SamsungLabs / ASAM
Implementation of ASAM: Adaptive Sharpness-Aware Minimization for Scale-Invariant Learning of Deep Neural Networks, ICML 2021.
☆137Updated 3 years ago
Related projects: ⓘ
- Implementation of Visual Transformer for Small-size Datasets☆116Updated 2 years ago
- PyTorch repository for ICLR 2022 paper (GSAM) which improves generalization (e.g. +3.8% top-1 accuracy on ImageNet with ViT-B/32)☆137Updated 2 years ago
- Whitening for Self-Supervised Representation Learning | Official repository☆123Updated last year
- Unofficial implementation of MLP-Mixer: An all-MLP Architecture for Vision☆207Updated 3 years ago
- Official PyTorch implementation of "Puzzle Mix: Exploiting Saliency and Local Statistics for Optimal Mixup" (ICML'20)☆158Updated 2 years ago
- Recent Advances in MLP-based Models (MLP is all you need!)☆112Updated last year
- Code for paper "Orthogonal Convolutional Neural Networks".☆110Updated 3 years ago
- NeurIPS 2021, Official codes for "Efficient Training of Visual Transformers with Small Datasets".☆138Updated last year
- [BMVC 2022] Official repository for "How to Train Vision Transformer on Small-scale Datasets?"☆139Updated 10 months ago
- PyTorch implementation of SimCLR: supports multi-GPU training and closely reproduces results☆187Updated 4 months ago
- ☆31Updated last year
- Pytorch implementation of the paper Exploring Simple Siamese Representation Learning.☆64Updated 3 years ago
- (ICML 2022) Official PyTorch implementation of “Blurs Behave Like Ensembles: Spatial Smoothings to Improve Accuracy, Uncertainty, and Rob…☆76Updated 2 years ago
- ICLR 2021 i-Mix: A Domain-Agnostic Strategy for Contrastive Representation Learning☆77Updated 8 months ago
- Transformers trained on Tiny ImageNet☆46Updated 2 years ago
- Official Implementation of SWAD (NeurIPS 2021)☆151Updated last year
- ☆57Updated last year
- Transformers w/o Attention, based fully on MLPs☆85Updated 5 months ago
- TF/Keras code for DiffStride, a pooling layer with learnable strides.☆123Updated 2 years ago
- PyTorch implementation for Vision Transformer[Dosovitskiy, A.(ICLR'21)] modified to obtain over 90% accuracy FROM SCRATCH on CIFAR-10 wit…☆167Updated 7 months ago
- Train ImageNet *fast* in 500 lines of code with FFCV☆135Updated 4 months ago
- Reproduce CKA: Similarity of Neural Network Representations Revisited☆274Updated 4 years ago
- Official Pytorch implementation of "Learning Debiased Representation via Disentangled Feature Augmentation (Neurips 2021, Oral)"☆98Updated last year
- The official repo for CVPR2023 highlight paper "Gradient Norm Aware Minimization Seeks First-Order Flatness and Improves Generalization".☆76Updated last year
- Pytorch reimplementation of the Mixer (MLP-Mixer: An all-MLP Architecture for Vision)☆32Updated 3 years ago
- This repo is for our paper: Normalization Techniques in Training DNNs: Methodology, Analysis and Application☆84Updated 3 years ago
- [NeurIPS 2021]: Are Transformers More Robust Than CNNs? (Pytorch implementation & checkpoints)☆175Updated 2 years ago
- Confidence-Aware Learning for Deep Neural Networks (ICML2020)☆72Updated 4 years ago
- Simple CIFAR-10 classification with ConvMixer☆40Updated 2 years ago
- Implementation of Barlow Twins paper☆99Updated last year